# US 12,499,259 B2 · Personally identifiable information comparison to dynamic industry state > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,499,259 B2 - Document ID: US12499259B2 - Status: Granted - Kind: B2 - Application number: 18/212,109 - Filed: 2023-06-20 - Published: 2023-12-21 - Granted: 2025-12-16 - Earliest claimed: 2022-06-20 - Assignees: Reltio, Inc. - Applicants: Reltio, Inc. - Inventors: Michael Burke; Jordan Hardy; Alexander Huitric; Nilesh Mishra; Manish Sood; Robin Sylvester - Web page: https://patentgrep.com/patent/US12499259B2 ## CPC - G06F 21/6218: {to a system of files or objects, e.g. local or distributed file system or database} - G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Among other techniques, techniques for providing feedback associated with personally identifiable information (PII) to a customer that is a member of an industry are described. The feedback includes a comparison with dynamic industry state. A system utilizing these techniques can include a continuous initially personally identifiable information (IPII) destruction engine; an IPII feature extraction engine coupled to the continuous IPII destruction engine; a bit labeling engine coupled to the continuous IPII destruction engine; a classified and interpreted IPII attribute instance bits datastore coupled to the bit labeling engine; and an auto-meta comparator feedback engine coupled to the classified and interpreted IPII attribute instance bits datastore. A method utilizing these techniques can include subdividing into affixes initially personally identifiable information (IPII) attribute instances of a first customer of a plurality of customers that are part of an industry; outputting bits corresponding to the IPII attribute instances; attaching labels to the bits, which are stored with metadata; and providing feedback to the first customer for the IPII attribute instances along with a dynamic auto-metadata comparison relative to dynamic industry state of the industry, wherein IPII attribute instances of the plurality of customers are used to update the dynamic industry state. ## Claims ### Claim 1 A system comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the system to perform: subdividing into affixes initially personally identifiable information (IPII) attribute instances of a first customer of a plurality of customers that are part of an industry: outputting bits corresponding to the IPII attribute instances; attaching labels to the bits, which are stored with metadata; providing feedback to the first customer for the IPII attribute instances along with a dynamic auto-metadata comparison relative to a dynamic benchmark, wherein IPII attribute instances of the plurality of customers are used to update the dynamic benchmark. ### Claim 2 (depends on 1) The system of claim 1, comprising a customer datastore that includes raw data from one or more customer systems, wherein the raw data includes one or more of personally identifiable information (PII), a hash or other derived value of the PII, and data associated with the PII. ### Claim 3 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to convert personally identifiable information (PII) attribute instances to the IPII attribute instances. ### Claim 4 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to convert the IPII attribute instances to personally identifiable information (PII) attribute instances. ### Claim 5 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to hash the IPII prior to feature extraction. ### Claim 6 (depends on 1) The system of claim 1, wherein the dynamic auto-metadata comparison is generated using the dynamic benchmark. ### Claim 7 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to subdivide the IPII attribute instances into affixes. ### Claim 8 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to use microservices to enrich data associated with the affixes. ### Claim 9 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to use IPII-aware microservices to provide micro-weights to specific data types, and wherein the metadata includes micro-weight metadata. ### Claim 10 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to assess the bits corresponding to the IPII attribute instances, the metadata, and raw data. ### Claim 11 (depends on 1) The system of claim 1, wherein the labels are attached to the bits during a training step. ### Claim 12 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to use ownership metadata and source system metadata. ### Claim 13 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to run the bits and the metadata through a model to obtain a classified label. ### Claim 14 (depends on 1) The system of claim 1, wherein the IPII attribute instances are broken apart and statistics are performed on rearranged data to locate minimums, maximums, averages, and freshness associated with the IPII attribute instances. ### Claim 15 (depends on 1) The system of claim 1, wherein the dynamic auto-metadata comparison is incorporated into a real-time (RT) landing for extract, transform, and loading (ETL). ### Claim 16 (depends on 1) The system of claim 1, wherein the instructions when executed by the one or more processors, cause the system to provide feedback that facilitates identifying uniqueness at industry level. ### Claim 17 (depends on 1) The system of claim 1, wherein the feedback includes recommendations, suggestions regarding how to amplify recommendations, and suggestions regarding how to get recommendations. ### Claim 18 (depends on 1) The system of claim 1, wherein the feedback relates to data quality. ### Claim 19 A method comprising: subdividing into affixes initially personally identifiable information (IPII) attribute instances of a first customer of a plurality of customers that are part of an industry; outputting bits corresponding to the IPII attribute instances; attaching labels to the bits, which are stored with metadata; providing feedback to the first customer for the IPII attribute instances along with a dynamic auto-metadata comparison relative to a dynamic benchmark, wherein IPII attribute instances of the plurality of customers are used to update the dynamic benchmark.